##// END OF EJS Templates
discovery: slowly increase sampling size...
discovery: slowly increase sampling size Some pathological discovery runs can requires many roundtrip. When this happens things can get very slow. To make the algorithm more resilience again such pathological case. We slowly increase the sample size with each roundtrip (+5%). This will have a negligible impact on "normal" discovery with few roundtrips, but a large positive impact of case with many roundtrips. Asking more question per roundtrip helps to reduce the undecided set faster. Instead of reducing the undecided set a linear speed (in the worst case), we reduce it as a guaranteed (small) exponential rate. The data below show this slow ramp up in sample size: round trip | 1 | 5 | 10 | 20 | 50 | 100 | 130 | sample size | 200 | 254 | 321 | 517 | 2 199 | 25 123 | 108 549 | covered nodes | 200 | 1 357 | 2 821 | 7 031 | 42 658 | 524 530 | 2 276 755 | To be a bit more concrete, lets take a very pathological case as an example. We are doing discovery from a copy of Mozilla-try to a more recent version of mozilla-unified. Mozilla-unified heads are unknown to the mozilla-try repo and there are over 1 million "missing" changesets. (the discovery is "local" to avoid network interference) Without this change, the discovery: - last 1858 seconds (31 minutes), - does 1700 round trip, - asking about 340 000 nodes. With this change, the discovery: - last 218 seconds (3 minutes, 38 seconds a -88% improvement), - does 94 round trip (-94%), - asking about 344 211 nodes (+1%). Of course, this is an extreme case (and 3 minutes is still slow). However this give a good example of how this sample size increase act as a safety net catching any bad situations. We could image a steeper increase than 5%. For example 10% would give the following number: round trip | 1 | 5 | 10 | 20 | 50 | 75 | 100 | sample size | 200 | 321 | 514 | 1 326 | 23 060 | 249 812 | 2 706 594 | covered nodes | 200 | 1 541 | 3 690 | 12 671 | 251 871 | 2 746 254 | 29 770 966 | In parallel, it is useful to understand these pathological cases and improve them. However the current change provides a general purpose safety net to smooth the impact of pathological cases. To avoid issue with older http server, the increase in sample size only occurs if the protocol has not limit on command argument size.

File last commit:

r41367:763b45bc default
r42546:dbd0fcca default
Show More
base85.c
203 lines | 3.8 KiB | text/x-c | CLexer
/*
base85 codec
Copyright 2006 Brendan Cully <brendan@kublai.com>
This software may be used and distributed according to the terms of
the GNU General Public License, incorporated herein by reference.
Largely based on git's implementation
*/
#define PY_SSIZE_T_CLEAN
#include <Python.h>
#include "util.h"
static const char b85chars[] =
"0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ"
"abcdefghijklmnopqrstuvwxyz!#$%&()*+-;<=>?@^_`{|}~";
static char b85dec[256];
static void b85prep(void)
{
unsigned i;
memset(b85dec, 0, sizeof(b85dec));
for (i = 0; i < sizeof(b85chars); i++) {
b85dec[(int)(b85chars[i])] = i + 1;
}
}
static PyObject *b85encode(PyObject *self, PyObject *args)
{
const unsigned char *text;
PyObject *out;
char *dst;
Py_ssize_t len, olen, i;
unsigned int acc, val, ch;
int pad = 0;
if (!PyArg_ParseTuple(args, PY23("s#|i", "y#|i"), &text, &len, &pad)) {
return NULL;
}
if (pad) {
olen = ((len + 3) / 4 * 5) - 3;
} else {
olen = len % 4;
if (olen) {
olen++;
}
olen += len / 4 * 5;
}
if (!(out = PyBytes_FromStringAndSize(NULL, olen + 3))) {
return NULL;
}
dst = PyBytes_AsString(out);
while (len) {
acc = 0;
for (i = 24; i >= 0; i -= 8) {
ch = *text++;
acc |= ch << i;
if (--len == 0) {
break;
}
}
for (i = 4; i >= 0; i--) {
val = acc % 85;
acc /= 85;
dst[i] = b85chars[val];
}
dst += 5;
}
if (!pad) {
_PyBytes_Resize(&out, olen);
}
return out;
}
static PyObject *b85decode(PyObject *self, PyObject *args)
{
PyObject *out = NULL;
const char *text;
char *dst;
Py_ssize_t len, i, j, olen, cap;
int c;
unsigned int acc;
if (!PyArg_ParseTuple(args, PY23("s#", "y#"), &text, &len)) {
return NULL;
}
olen = len / 5 * 4;
i = len % 5;
if (i) {
olen += i - 1;
}
if (!(out = PyBytes_FromStringAndSize(NULL, olen))) {
return NULL;
}
dst = PyBytes_AsString(out);
i = 0;
while (i < len) {
acc = 0;
cap = len - i - 1;
if (cap > 4) {
cap = 4;
}
for (j = 0; j < cap; i++, j++) {
c = b85dec[(int)*text++] - 1;
if (c < 0) {
PyErr_Format(
PyExc_ValueError,
"bad base85 character at position %d",
(int)i);
goto bail;
}
acc = acc * 85 + c;
}
if (i++ < len) {
c = b85dec[(int)*text++] - 1;
if (c < 0) {
PyErr_Format(
PyExc_ValueError,
"bad base85 character at position %d",
(int)i);
goto bail;
}
/* overflow detection: 0xffffffff == "|NsC0",
* "|NsC" == 0x03030303 */
if (acc > 0x03030303 || (acc *= 85) > 0xffffffff - c) {
PyErr_Format(
PyExc_ValueError,
"bad base85 sequence at position %d",
(int)i);
goto bail;
}
acc += c;
}
cap = olen < 4 ? olen : 4;
olen -= cap;
for (j = 0; j < 4 - cap; j++) {
acc *= 85;
}
if (cap && cap < 4) {
acc += 0xffffff >> (cap - 1) * 8;
}
for (j = 0; j < cap; j++) {
acc = (acc << 8) | (acc >> 24);
*dst++ = acc;
}
}
return out;
bail:
Py_XDECREF(out);
return NULL;
}
static char base85_doc[] = "Base85 Data Encoding";
static PyMethodDef methods[] = {
{"b85encode", b85encode, METH_VARARGS,
"Encode text in base85.\n\n"
"If the second parameter is true, pad the result to a multiple of "
"five characters.\n"},
{"b85decode", b85decode, METH_VARARGS, "Decode base85 text.\n"},
{NULL, NULL},
};
static const int version = 1;
#ifdef IS_PY3K
static struct PyModuleDef base85_module = {
PyModuleDef_HEAD_INIT, "base85", base85_doc, -1, methods,
};
PyMODINIT_FUNC PyInit_base85(void)
{
PyObject *m;
b85prep();
m = PyModule_Create(&base85_module);
PyModule_AddIntConstant(m, "version", version);
return m;
}
#else
PyMODINIT_FUNC initbase85(void)
{
PyObject *m;
m = Py_InitModule3("base85", methods, base85_doc);
b85prep();
PyModule_AddIntConstant(m, "version", version);
}
#endif